BF clawhub-skill-audit
Audit locally installed skills against ClawHub: detect version drift, find new publish candidates, review security flags, and triage ownership conflicts. Use when: reviewing whether published skills need updates, deciding what new local skills are ready to open-source, investigating hidden/flagged skills on ClawHub, or running the weekly skill lifecycle check.
As a process F 33/100 · Will not run — References files that are not bundled: scripts/skill-lifecycle/drift-detector.py, scripts/clawhub_audit.py, scripts/skill-lifecycle/publish-skill.sh
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/skill-lifecycle/drift-detector.py - warning
missing-refreference to a missing file: scripts/clawhub_audit.py - warning
missing-refreference to a missing file: scripts/skill-lifecycle/publish-skill.sh
Process rating: all ten parameters 33/100
- 0Tools and files. 3 referenced file(s) missing: scripts/skill-lifecycle/drift-detector.py, scripts/clawhub_audit.py, scripts/skill-lifecycle/publish-skill.sh
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 15 mutating operations with no state check
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1140 tokens
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 362: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.